Slope engineering is a type of complex system engineering that is mostly involved in water conservancy and civil and mining engineering. Moreover, the link between slope stability and engineering safety is quite close. This study took the stable state of the slope as the prediction object and used the unit weight, cohesion, internal friction angle, pore water pressure coefficient, slope angle, and slope height as prediction indices to analyze the slope stability based on the collection of 117 slope data points. The genetic algorithm was used to solve the hyperparameters of machine learning algorithms by simulating the phenomena of reproduction, hybridization, and mutation in the natural selection and natural genetic processes. Five algorithms were used, including the support vector machine, random forest, nearest neighbor, decision tree, and gradient boosting machine models. Finally, all of the obtained stability prediction results were compared. The prediction outcomes were analyzed using the confusion matrix, receiver characteristic operator (ROC), and area under the curve (AUC) value. The AUC values of all machine learning prediction results were between 0.824 and 0.964, showing excellent performance. Considering the AUC value, accuracy, and other factors, the random forest algorithm with KS cutoff was determined to be the optimal model, and the relative importance of the influencing variables was studied. The results show that cohesion was the factor that most affects slope stability, and the influence factor was 0.327. This study proves the effectiveness of the integrated techniques for slope stability prediction, makes essential suggestions for future slope stability analysis, and may be extensively applied in other industrial projects.

Dust pollution in open-pit coal mines severely restricts the green development of mines. Therefore, dust control has become an important requirement for the sustainable development of the mining industry. With the goal of dust pollution prevention and control in open-pit coal mines, this paper puts forward the concept of a non-disturbance area of an open-pit coal mine. It clarifies the characteristics of dust generation, the coverage area, and the dust particle size distribution characteristics of the non-disturbance area. Taking the dust control at the dump site as an example, the study comprehensively utilizes indoor tests and field tests to develop a dust suppressant for the dump site and determine its dust suppression efficiency and effective service cycle. The results show that the D10, D50, and D90 particle sizes of dust in the non-disturbance area are smaller than those in the disturbance area, and the difference in particle size of D90 is the most obvious. Gelatinized starch and non-ionic polyacrylamide, as the main components of the dust suppressant, can effectively reduce dust pollution in the dump; the optimal concentration is 1.0%, and the dust suppression service cycle is more than one month. The developed dust suppressant does not contain corrosive, toxic, or heavy metal elements. Although the application of a dust suppressant will cause plant growth to lag, it does not affect plant health. The research findings serve as a reference for the zoning treatment of dust in open-pit mines.

Dust is a severe environmental issue in open-pit mines, and accurate estimation of its concentration allows for viable solutions for its control and management. This research proposes a machine learning-based solution for accurately estimating dust concentrations. The proposed approach, tested using real data from the Haerwusu open-pit coal mine in China, is based upon the integrated random forest-Markov chain (RF-MC) model. The random forest method is used for estimation, while the Markov chain is used for estimation correction. The wind speed, temperature, humidity, and atmospheric pressure are used as inputs, while PM2.5, PM10, and TSP are taken as estimated outputs. A detailed procedure for implementing the RF-MC is presented, and the estimated performance is analyzed. The results show that after correction, the root mean squared error significantly decreased from 7.40 to 2.56 μg/m³ for PM2.5, from 15.73 to 5.28 μg/m³ for PM10, and from 18.99 to 6.27 μg/m³ for TSP, and the Pearson correlation coefficient and the mean absolute error also improved considerably. This work provides an improved machine learning approach for dust concentration estimation in open-pit coal mines, with a greater emphasis on simplicity and rapid model updates, which is more applicable to ensure the prudent use of water resources and overall environmental conservation, both of which are advantageous to green mining.

This research proposes a new dust reduction method based on water infusion blasting in order to effectively minimize the dust production during blasting in open-pit mines. The proposed method was applied at the Haerwusu open-pit coal mine, China. A high-speed camera was used to record the dynamic process of dust generation during blasting. The images acquired from the main locations of the dust were analyzed using the gray level recognition method in MATLAB. The proposed method was then numerically simulated using ANSYS/Fluent software. Finally, the field experiment was conducted to verify the method by analyzing its dust reduction efficiency. The numerical results show that the dust reduction rate of about 78% can be achieved when the water bag is filled at the height of 1.8 m according to the blast design parameters of the mine (burden = 11 m, spacing = 7 m, hole diameter = 0.25 m, hole depth = 20 m). The experimental results achieved a 75% dust reduction rate, which meets the requirements of reducing blasting dust pollution in the studied mine. These investigations and findings conclude that the proposed method is effective, technically feasible, and economical. It can be widely applied to other open-pit mines as a green mining technology.